University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Event-based Multitrack Alignment using a Probabilistic Framework

Robertson, A and Plumbley, MD (2015) Event-based Multitrack Alignment using a Probabilistic Framework Journal of New Music Research, 44 (2). pp. 71-82.

[img] Text
RobertsonPlumbley15-jnmr_v5-accepted.pdf
Restricted to Repository staff only until 15 March 2017.
Available under License : See the attached licence file.

Download (476kB)
[img]
Preview
Text (licence)
SRI_deposit_agreement.pdf
Available under License : See the attached licence file.

Download (33kB) | Preview

Abstract

© 2015 Taylor & Francis. This paper presents a Bayesian probabilistic framework for real-time alignment of a recording or score with a live performance using an event-based approach. Multitrack audio files are processed using existing onset detection and harmonic analysis algorithms to create a representation of a musical performance as a sequence of time-stamped events. We propose the use of distributions for the position and relative speed which are sequentially updated in real-time according to Bayes’ theorem. We develop the methodology for this approach by describing its application in the case of matching a single MIDI track and then extend this to the case of multitrack recordings. An evaluation is presented that contrasts ourmultitrack alignment method with state-of-the-art alignment techniques.

Item Type: Article
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering > Centre for Vision Speech and Signal Processing
Authors :
AuthorsEmailORCID
Robertson, AUNSPECIFIEDUNSPECIFIED
Plumbley, MDUNSPECIFIEDUNSPECIFIED
Date : 1 January 2015
Identification Number : 10.1080/09298215.2015.1009839
Additional Information : This is an Accepted Manuscript of an article published by Taylor & Francis in Journal of New Music Research on 14 September 2015, available online: http://wwww.tandfonline.com/10.1080/09298215.2015.1009839
Depositing User : Symplectic Elements
Date Deposited : 10 Nov 2015 15:32
Last Modified : 10 Nov 2015 15:32
URI: http://epubs.surrey.ac.uk/id/eprint/809246

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800